Exportar Publicação

Cosme, D., Galvão, A. & Brito e Abreu, F. (2024). A Systematic Literature Review on LLM-Based Information Retrieval: The Issue of Contents Classification. In Frans Coenen; Ana Fred, Jorge Bernardino (Ed.), Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management. (pp. 135-146). Porto, Portugal: SCITEPRESS - Science and Technology Publications.

D. F. Cosme et al.,  "A Systematic Literature Review on LLM-Based Information Retrieval: The Issue of Contents Classification", in Proc. of the 16th Int. Joint Conf. on Knowledge Discovery, Knowledge Engineering and Knowledge Management, Frans Coenen; Ana Fred, Jorge Bernardino, Ed., Porto, Portugal, SCITEPRESS - Science and Technology Publications, 2024, pp. 135-146

@inproceedings{cosme2024_1734956137955,
	author = "Cosme, D. and Galvão, A. and Brito e Abreu, F.",
	title = "A Systematic Literature Review on LLM-Based Information Retrieval: The Issue of Contents Classification",
	booktitle = "Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management",
	year = "2024",
	editor = "Frans Coenen; Ana Fred, Jorge Bernardino",
	volume = "",
	number = "",
	series = "",
	doi = "10.5220/0013062300003838",
	pages = "135-146",
	publisher = "SCITEPRESS - Science and Technology Publications",
	address = "Porto, Portugal",
	organization = "INSTICC",
	url = "https://kdir.scitevents.org"
}

TY  - CPAPER
TI  - A Systematic Literature Review on LLM-Based Information Retrieval: The Issue of Contents Classification
T2  - Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management
AU  - Cosme, D.
AU  - Galvão, A.
AU  - Brito e Abreu, F.
PY  - 2024
SP  - 135-146
DO  - 10.5220/0013062300003838
CY  - Porto, Portugal
UR  - https://kdir.scitevents.org
AB  - This paper conducts a systematic literature review on applying Large Language Models (LLMs) in information retrieval, specifically focusing on content classification. The review explores how LLMs, particularly those based on transformer architectures, have addressed long-standing challenges in text classification by leveraging their advanced context understanding and generative capabilities. Despite the rapid advancements, the review identifies gaps in current research, such as the need for improved transparency, reduced computational costs, and the handling of model hallucinations. The paper concludes with recommendations for future research directions to optimize the use of LLMs in content classification, ensuring their effective deployment across various domains.
ER  -